Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    python code definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iest
    1.10
    이나
    1.09
    ipe
    1.07
     sẽ
    1.07
     când
    1.06
    */
    1.04
    会
    1.02
    mav
    0.98
    ávan
    0.98
    iat
    0.97
    POSITIVE LOGITS
    ны
    1.49
    ע
    1.26
    什么是
    1.23
    س
    1.20
    いろんな
    1.15
    9
    1.13
    6
    1.09
    enje
    1.08
     cataracts
    1.03
    7
    1.03
    Act Density 0.033%

    No Known Activations